Diagnosis of Peripheral Artery Disease Using Backflow Abnormalities in Proximal Recordings of Accelerometer Contact Microphone (ACM).

OBJECTIVE: The development of an accurate, non-invasive method for the diagnosis of peripheral artery disease (PAD) from accelerometer contact microphone (ACM) recordings of the cardiac system. METHODS: Mel frequency cepstral coefficients (MFCCs) are initially extracted from ACM recordings. The extracted MFCCs are then used to fine-tune a pre-trained ResNet50 network whose middle layers provide streams of high-level-of-abstraction coefficients (HLACs) which could provide information on blood pressure backflow caused by arterial obstructions in PAD patients. A vision transformer is finally integrated with the feature extraction layer to detect PAD, and stratify the severity level. This architecture is coined multi-stream-powered vision transformer (MSPViT). The performance of MSPViT is evaluated on 74 PAD and 21 healthy subjects. RESULTS: Sensitivity, specificity, F1 score, and area under the curve (AUC) of 99.45%, 98.21%, 99.37%, and 0.99, respectively, are reported for the binary classification which ensures accurate detection of PAD. Furthermore, MSPViT suggests average sensitivity, specificity, F1 score, and AUC of 96.66%, 97.34%, 96.29%, and 0.96, respectively, for the classification of subjects into healthy, mild-PAD, and severe-PAD classes. The silhouette score is calculated to assess the separability of clusters formed for classes in the penultimate layer of MSPViT. An average silhouette score of 0.66 and 0.81 demonstrate excellent cluster separability in PAD detection and severity classification, respectively. CONCLUSION: The achieved performance suggests that the proximal ACM-driven framework can replace state-of-the-art techniques for PAD detection. SIGNIFICANCE: This study presents a fundamental step towards prompt and accurate diagnosis of PAD and stratification of its severity level.

Fetal Electrocardiogram Extraction Using Dual-Path Source Separation of Single-Channel Non-Invasive Abdominal Recordings.

OBJECTIVE: The development of a method for non-invasive monitoring of fetal electrocardiogram (FECG) signals from single-channel abdominal recordings. METHODS: The dual-path source separation (DPSS) architecture is introduced for the simultaneous separation of fetal and maternal ECG signals from abdominal ECG recordings. DPSS initially denoises abdominal ECG (AECG) recordings using a generative dual-path long short-term memory (DP-LSTM) network. An inception module along with a series of DP-LSTM blocks is then employed to extract the masking maps associated with fetal and maternal components. Finally, these masking maps are weighted by the AECG recording to separate maternal and fetal ECG signals. The performance of this network is evaluated on 10 pregnancies from the fetal ECG synthetic database (FECGSYNDB), 22 cases of labor and pregnancy from the abdominal and direct fetal ECG database (ADFECGDB), and 69 pregnancies from set A of non-invasive FECG challenge (NIFECGC) datasets. RESULTS: F1-scores of 99.03%, 97.7%, and 95.3% are reported for the detection of fetal QRS complexes in FECGSYNDB, ADFECGDB, and NIFECGC respectively. DPSS technique is also evaluated in terms of separability of fetal and maternal clusters. According to the clustering-based analyses, the average purity index of 0.9750, Jaccard index of 0.9705, and Davies-Bouldin index of 0.7429 demonstrate the high source separation capability of DPSS. CONCLUSION: The achieved performance suggests that DPSS enables accurate single-channel FECG extraction, and can replace state-of-the-art source separation techniques for this purpose. SIGNIFICANCE: This study signifies a fundamental step towards non-invasive fetal ECG monitoring systems, which favors at-home prenatal care.

Fetal Movement Cancellation in Abdominal Electrocardiogram Recordings Using Signal-to-Signal Translation.

This study addresses the cancellation of fetal movement in abdominal electrocardiogram (AECG) recordings through deep neural networks. For this purpose, a generative signal-to-signal translation model consisting of two coupled generators is employed to discover the relations between fetal movement-contaminated and clean AECG recordings. The model is trained on the fetal ECG synthetic database (FECGSYNDB) which provides AECG recordings from 10 pregnancies along with their ground-truth maternal and fetal ECG signals. The signals are initially segmented into 4-second segments and then fed into the network for denoising. It is demonstrated that the signal-to-signal translation method can reconstruct clean AECG signals with average mean-absolute-error (MAE), root-mean-square deviation (RMSD), and Pearson correlation coefficient (PCC) of 0.099, 0.124, and 99.12% respectively, between clean and denoised AECG signals. Furthermore, the robustness of the method to low signal-to-noise ratio (SNR) input values is shown by an RMSD range of (0.047, 0.352) for SNR values within the range of (-3, 3) dB. Clinical Relevance- The proposed framework allows for the denoising of abdominal ECG signals for non-invasive fetal heart rate monitoring. The approach is accurate due to the use of advanced neural network techniques.

Real-time high-resolution millimeter-wave imaging for in-vivo skin cancer diagnosis.

High-resolution millimeter-wave imaging (HR-MMWI), with its high discrimination contrast and sufficient penetration depth, can potentially provide affordable tissue diagnostic information noninvasively. In this study, we evaluate the application of a real-time system of HR-MMWI for in-vivo skin cancer diagnosis. 136 benign and malignant skin lesions from 71 patients, including melanoma, basal cell carcinoma, squamous cell carcinoma, actinic keratosis, melanocytic nevi, angiokeratoma, dermatofibroma, solar lentigo, and seborrheic keratosis were measured. Lesions were classified using a 3-D principal component analysis followed by five classifiers including linear discriminant analysis (LDA), K-nearest neighbor (KNN) with different K-values, linear and Gaussian support vector machine (LSVM and GSVM) with different margin factors, and multilayer perception (MLP). Our results suggested that the best classification was achieved by using five PCA components followed by MLP with 97% sensitivity and 98% specificity. Our findings establish that real-time millimeter-wave imaging can be used to distinguish malignant tissues from benign skin lesions with high diagnostic accuracy comparable with clinical examination and other methods.

Multi-modal Framework for Fetal Heart Rate Estimation: Fusion of Low-SNR ECG and Inertial Sensors.

This study presents a novel multi-modal framework for fetal heart rate extraction, which incorporates wearable seismo-cardiography (SCG), gyro-cardiography (GCG), and electrocardiography (ECG) readings from ten pregnant women. Firstly, a signal refinement method based on empirical mode decomposition (EMD) is proposed to extract the desired signal components associated with fetal heart rate (FHR). Afterwards, two techniques are developed to fuse the information from different modalities. The first method, named early fusion, is intended to combine the refined signals of different modalities through intra-modality fusion, intermodality fusion, and FHR estimation. The other fusion approach, i.e., late fusion, includes FHR estimation and intermodality FHR fusion. FHR values are estimated and compared with readings from a simultaneously-recorded cardiotocography (CTG) sensor. It is demonstrated that the best performance belongs to the late-fusion approach with 87.00% of positive percent agreement (PPA), 6.30% of absolute percent error (APE), and 10.55 beats-per-minute (BPM) of root-meansquare-error (RMSE).Clinical Relevance- The proposed framework allows for the continuous monitoring of the health status of the fetus in expectant women. The approach is accurate and cost-effective due to the use of advanced signal processing techniques and lowcost wearable sensors, respectively.

Mean Pressure Gradient Prediction Based on Chest Angular Movements and Heart Rate Variability Parameters.

This study presents our recent findings on the classification of mean pressure gradient using angular chest movements in aortic stenosis (AS) patients. Currently, the severity of aortic stenosis is measured using ultra-sound echocardiography, which is an expensive technology. The proposed framework motivates the use of low-cost wearable sensors, and is based on feature extraction from gyroscopic readings. The feature space consists of the cardiac timing intervals as well as heart rate variability (HRV) parameters to determine the severity of disease. State-of-the-art machine learning (ML) methods are employed to classify the severity levels into mild, moderate, and severe. The best performance is achieved by the Light Gradient-Boosted Machine (Light GBM) with an F1-score of 94.29% and an accuracy of 94.44%. Additionally, game theory-based analyses are employed to examine the top features along with their average impacts on the severity level. It is demonstrated that the isovolumetric contraction time (IVCT) and isovolumetric relaxation time (IVRT) are the most representative features for AS severity.Clinical Relevance- The proposed framework could be an appropriate low-cost alternative to ultra-sound echocardiography, which is a costly method.

Efficient detection of aortic stenosis using morphological characteristics of cardiomechanical signals and heart rate variability parameters.

Recent research has shown promising results for the detection of aortic stenosis (AS) using cardio-mechanical signals. However, they are limited by two main factors: lacking physical explanations for decision-making on the existence of AS, and the need for auxiliary signals. The main goal of this paper is to address these shortcomings through a wearable inertial measurement unit (IMU), where the physical causes of AS are determined from IMU readings. To this end, we develop a framework based on seismo-cardiogram (SCG) and gyro-cardiogram (GCG) morphologies, where highly-optimized algorithms are designed to extract features deemed potentially relevant to AS. Extracted features are then analyzed through machine learning techniques for AS diagnosis. It is demonstrated that AS could be detected with 95.49-100.00% confidence. Based on the ablation study on the feature space, the GCG time-domain feature space holds higher consistency, i.e., 95.19-100.00%, with the presence of AS than HRV parameters with a low contribution of 66.00-80.00%. Furthermore, the robustness of the proposed method is evaluated by conducting analyses on the classification of the AS severity level. These analyses are resulted in a high confidence of 92.29%, demonstrating the reliability of the proposed framework. Additionally, game theory-based approaches are employed to rank the top features, among which GCG time-domain features are found to be highly consistent with both the occurrence and severity level of AS. The proposed framework contributes to reliable, low-cost wearable cardiac monitoring due to accurate performance and usage of solitary inertial sensors.

An Open-Access Database for the Evaluation of Cardio-Mechanical Signals From Patients With Valvular Heart Diseases.

This paper describes an open-access database for seismo-cardiogram (SCG) and gyro-cardiogram (GCG) signals. The archive comprises SCG and GCG recordings sourced from and processed at multiple sites worldwide, including Columbia University Medical Center and Stevens Institute of Technology in the United States, as well as Southeast University, Nanjing Medical University, and the first affiliated hospital of Nanjing Medical University in China. It includes electrocardiogram (ECG), SCG, and GCG recordings collected from 100 patients with various conditions of valvular heart diseases such as aortic and mitral stenosis. The recordings were collected from clinical environments with the same types of wearable sensor patch. Besides the raw recordings of ECG, SCG, and GCG signals, a set of hand-corrected fiducial point annotations is provided by manually checking the results of the annotated algorithm. The database also includes relevant echocardiogram parameters associated with each subject such as ejection fraction, valve area, and mean gradient pressure.

A Hybrid Radar-Camera Respiratory Monitoring System Based on an Impulse-Radio Ultrawideband Radar.

This paper reports a pilot study of a hybrid radar-camera system that simultaneously monitors the respiration of two subjects. A prototype system was built involving a low-cost impulse-radio ultra-wideband (IR-UWB) radar module and an optical and depth-sensing camera module. The system detects subjects using the camera and utilizes the distance information acquired to guide the signal processing of the radar. This structure simplifies subject identification and tracking for the radar system, provides further context to the radar, and facilitates the extraction of respiration information. Experiments under different scenarios were conducted to evaluate the performance of the system at different distances and angles from subjects. The localization procedure has an average accuracy of 0.1 m. The respiration rates extracted from the radar are comparable with the values from the reference wearable sensor, reporting an average error of 0.79 respirations per minute (RPM) with a standard deviation of 0.71 RPM. The results suggest that the respiration signals from subjects could be accurately monitored with the presented framework. It is also feasible to monitor two subjects at the same time in most scenarios. The proposed framework shows promising potential to work as a ubiquitous monitoring system for multiple subjects.

Classification of Aortic Stenosis Before and After Transcatheter Aortic Valve Replacement Using Cardio-mechanical Modalities.

This paper reports our study on the impact of transcatheter aortic valve replacement (TAVR) on the classification of aortic stenosis (AS) patients using cardio-mechanical modalities. Machine learning algorithms such as decision tree, random forest, and neural network were applied to conduct two tasks. Firstly, the pre- and post-TAVR data are evaluated with the classifiers trained in the literature. Secondly, new classifiers are trained to classify between pre- and post-TAVR data. Using analysis of variance, the features that are significantly different between pre- and post-TAVR patients are selected and compared to the features used in the pre-trained classifiers. The results suggest that pre-TAVR subjects could be classified as AS patients but post-TAVR could not be classified as healthy subjects. The features which differentiate pre- and post-TAVR patients reveal different distributions compared to the features that classify AS patients and healthy subjects. These results could guide future work in the classification of AS as well as the evaluation of the recovery status of patients after TAVR treatment.

A Fetal Movement Simulation System for Wearable Vibrational Sensors.

This paper introduces a low-cost phantom system that simulates fetal movements (FMVs) for the first time. This vibration system can be used for testing wearable inertial sensors which detect FMVs from the abdominal wall. The system consists of a phantom abdomen, a linear stage with a stepper motor, a tactile transducer, and control circuits. The linear stage is used to generate mechanical vibrations which are transferred to the latex abdomen. A tactile transducer is implemented to add environmental noise to the system. The system is characterized and tested using a wireless sensor. The sensor recordings are analyzed using time-frequency analysis and the results are compared to real FMVs reported in the literature. Experiments are conducted to characterize the vibration range, frequency response, and noise generation of the system. It is shown that the system is effective in simulating the vibration of fetal movements, covering the full frequency and magnitude ranges of real FMV vibrations. The noise generation test shows that the system can effectively create scenarios with different signal-to-noise ratios for FMV detection. The system can facilitate the development of fetal movement monitoring systems and algorithms.

Classification of aortic stenosis using conventional machine learning and deep learning methods based on multi-dimensional cardio-mechanical signals.

This paper introduces a study on the classification of aortic stenosis (AS) based on cardio-mechanical signals collected using non-invasive wearable inertial sensors. Measurements were taken from 21 AS patients and 13 non-AS subjects. A feature analysis framework utilizing Elastic Net was implemented to reduce the features generated by continuous wavelet transform (CWT). Performance comparisons were conducted among several machine learning (ML) algorithms, including decision tree, random forest, multi-layer perceptron neural network, and extreme gradient boosting. In addition, a two-dimensional convolutional neural network (2D-CNN) was developed using the CWT coefficients as images. The 2D-CNN was made with a custom-built architecture and a CNN based on Mobile Net via transfer learning. After the reduction of features by 95.47%, the results obtained report 0.87 on accuracy by decision tree, 0.96 by random forest, 0.91 by simple neural network, and 0.95 by XGBoost. Via the 2D-CNN framework, the transfer learning of Mobile Net shows an accuracy of 0.91, while the custom-constructed classifier reveals an accuracy of 0.89. Our results validate the effectiveness of the feature selection and classification framework. They also show a promising potential for the implementation of deep learning tools on the classification of AS.

Classification of Aortic Stenosis Using Time-Frequency Features From Chest Cardio-Mechanical Signals.

OBJECTIVES: This paper introduces a novel method for the detection and classification of aortic stenosis (AS) using the time-frequency features of chest cardio-mechanical signals collected from wearable sensors, namely seismo-cardiogram (SCG) and gyro-cardiogram (GCG) signals. Such a method could potentially monitor high-risk patients out of the clinic. METHODS: Experimental measurements were collected from twenty patients with AS and twenty healthy subjects. Firstly, a digital signal processing framework is proposed to extract time-frequency features. The features are then selected via the analysis of variance test. Different combinations of features are evaluated using the decision tree, random forest, and artificial neural network methods. Two classification tasks are conducted. The first task is a binary classification between normal subjects and AS patients. The second task is a multi-class classification of AS patients with co-existing valvular heart diseases. RESULTS: In the binary classification task, the average accuracies achieved are 96.25% from decision tree, 97.43% from random forest, and 95.56% from neural network. The best performance is from combined SCG and GCG features with random forest classifier. In the multi-class classification, the best performance is 92.99% using the random forest classifier and SCG features. CONCLUSION: The results suggest that the solution could be a feasible method for classifying aortic stenosis, both in the binary and multi-class tasks. It also indicates that most of the important time-frequency features are below 11 Hz. SIGNIFICANCE: The proposed method shows great potential to provide continuous monitoring of valvular heart diseases to prevent patients from sudden critical cardiac situations.

A Fast Parameter Identification Framework for Personalized Pharmacokinetics.

This paper introduces a novel framework for fast parameter identification of personalized pharmacokinetic problems. Given one sample observation of a new subject, the framework predicts the parameters of the subject based on prior knowledge from a pharmacokinetic database. The feasibility of this framework was demonstrated by developing a new algorithm based on the Cluster Newton method, namely the constrained Cluster Newton method, where the initial points of the parameters are constrained by the database. The algorithm was tested with the compartmental model of propofol on a database of 59 subjects. The average overall absolute percentage error based on constrained Cluster Newton method is 12.10% with the threshold approach, and 13.42% with the nearest-neighbor approach. The average computation time of one estimation is 13.10 seconds. Using parallel computing, the average computation time is reduced to 1.54 seconds, achieved with 12 parallel workers. The results suggest that the proposed framework can effectively improve the prediction accuracy of the pharmacokinetic parameters with limited observations in comparison to the conventional methods. Computation cost analyses indicate that the proposed framework can take advantage of parallel computing and provide solutions within practical response times, leading to fast and accurate parameter identification of pharmacokinetic problems.

A Smartphone-Only Pulse Transit Time Monitor Based on Cardio-Mechanical and Photoplethysmography Modalities.

This paper reports a system for monitoring pulse transit time (PTT). Using an Android smartphone and a customized sensing circuit, the system collects seismo-cardiogram (SCG), gyro-cardiogram (GCG), and photoplethysmogram (PPG) recordings. There is no need for any other external stand-alone systems. The SCG and GCG signals are recorded with the inertial sensors of the smartphone, while the PPG signal is recorded using a sensing circuit connected to the audio jack of the phone. The sensing circuit is battery-less, powered by the audio output of the smartphone using an energy harvester that converts audio tones into DC power. PPG waveforms are sampled via the microphone channel. A signal processing framework is developed and the system is experimentally verified on twenty healthy subjects at rest. The PTT is measured as the time difference between the aortic valve (AO) opening points in SCG or GCG and the fiducial points in PPG. The root-mean-square errors between the results from a stand-alone sensor system and the proposed system report 3.9 ms from SCG-based results and 3.4 ms from GCG-based results. The detection rates report more than 97.92% from both SCG and GCG results. This performance is comparable with stand-alone sensor nodes at a much lower cost.

High-Contrast, Low-Cost, 3-D Visualization of Skin Cancer Using Ultra-High-Resolution Millimeter-Wave Imaging.

The goal of this paper is to develop a new skin imaging modality which addresses the current clinical need for a non-invasive imaging tool that images the skin over its depth with high resolutions while offering large histopathological-like contrasts between malignant and normal tissues. We demonstrate that by taking advantage of the intrinsic millimeter-wave dielectric contrasts between normal and malignant skin tissues, ultra-high-resolution millimeter-wave imaging (MMWI) can achieve 3-D, high-contrast images of the skin. In this paper, an imaging system with a record-wide bandwidth of 98 GHz is developed using the synthetic ultra-wideband millimeter-wave imaging approach, a new ultra-high-resolution imaging technique recently developed by the authors. The 21 non-melanoma skin cancer (NMSC) specimens are imaged and compared with histopathology for evaluation. A programmable measurement platform is designed to automatically scan the tissues across a rectangular aperture plane. Furthermore, a novel frequency-domain imaging algorithm is developed to process the recorded signals and generate an image of the cancerous tissue. The high correlations achieved between MMWI images and histological images allow for rapid and accurate delineation of NMSC tissues. The millimeter-wave reflectivity values are also found to be statistically significant higher for cancerous areas with respect to normal areas. Since MMWI does not require tissue processing or staining, it can be performed promptly, enabling diagnosis of tumors at an early stage as well as simplify the tumor removal surgery to a single-layer excision procedure.

Ultrawideband, Stable Normal and Cancer Skin Tissue Phantoms for Millimeter-Wave Skin Cancer Imaging.

This work introduces new, stable, and broadband skin-equivalent semisolid phantoms for mimicking interactions of millimeter waves with the human skin and skin tumors. Realistic skin phantoms serve as an invaluable tool for exploring the feasibility of new technologies and improving design concepts related to millimeter-wave skin cancer detection methods. Normal and malignant skin tissues are separately mimicked by using appropriate mixtures of deionized water, oil, gelatin powder, formaldehyde, TX-150 (a gelling agent, widely referred to as "super stuff"), and detergent. The dielectric properties of the phantoms are characterized over the frequency band of 0.5-50 GHz using a slim-form open-ended coaxial probe in conjunction with a millimeter-wave vector network analyzer. The measured permittivity results show excellent match with ex vivo, fresh skin (both normal and malignant) permittivities determined in our prior work over the entire frequency range. This work results in the closest match among all phantoms reported in the literature to surrogate human skin tissues. The stability of dielectric properties over time is also investigated. The phantoms demonstrate long-term stability (up to 7 months was investigated). In addition, the penetration depth of millimeter waves into normal and malignant skin phantoms is calculated. It is determined that millimeter waves penetrate the human skin deep enough (0.6 mm on average at 50 GHz) to affect the majority of the epidermis and dermis skin structures.

Synthetic Ultra-High-Resolution Millimeter-Wave Imaging for Skin Cancer Detection.

This work introduces, for the first time, a millimeter-wave imaging system with a "synthetic" ultra-wide imaging bandwidth of 98 GHz to provide the ultra-high resolutions required for early-stage skin cancer detection. The proposed approach consists of splitting the required ultra-wide imaging bandwidth into four sub-bands, and assigning each sub-band to a separate imaging element, i.e., an antenna radiator. Each of the sub-band antennas transmits and receives signals only at its corresponding sub-band. The captured signals are then combined and processed to form the image of the target. For each sub-band, a Vivaldi tapered slot antenna fed with a combination of substrate-integrated waveguide and coplanar waveguide is designed and microfabricated. Design techniques are also provided for the four similarly-shaped sub-band antennas for achieving excellent impedance matches ( S11 < -10 dB) and nearly constant gains of 10 dBi over the entire 12-110 GHz bandwidth. The design procedure is validated by comparing the simulated results with measurements performed on the fabricated prototypes. Excellent agreements are obtained between simulations and measurements. Finally, the feasibility of detecting early-stage skin tumors in three dimensions is experimentally verified by employing the sub-band antennas in a synthetic ultra-wideband imaging system with a bandwidth of 98 GHz. Two separate setups, each comprising a dispersive skin-mimicking phantom as well as two dispersive spherical tumors, are constructed for imaging experiments. Lateral and axial resolutions of 200 µm are confirmed, and a successful reconstruction of the spherical tumors is achieved in both cases.

An Independent Component Analysis Approach to Motion Noise Cancelation of Cardio-Mechanical Signals.

This paper proposes a new framework for measuring sternal cardio-mechanical signals from moving subjects using multiple sensors. An array of inertial measurement units are attached to the chest wall of subjects to measure the seismocardiogram (SCG) from accelerometers and the gyrocardiogram (GCG) from gyroscopes. A digital signal processing method based on constrained independent component analysis is applied to extract the desired cardio-mechanical signals from the mixture of vibration observations. Electrocardiogram and photoplethysmography modalities are evaluated as reference sources for the constrained independent component analysis algorithm. Experimental studies with 14 young, healthy adult subjects demonstrate the feasibility of extracting seismo- and gyrocardiogram signals from walking and jogging subjects, with speeds of 3.0 mi/h and 4.6 mi/h, respectively. Beat-to-beat and ensemble-averaged features are extracted from the outputs of the algorithm. The beat-to-beat cardiac interval results demonstrate average detection rates of 91.44% during walking and 86.06% during jogging from SCG, and 87.32% during walking and 76.30% during jogging from GCG. The ensemble-averaged pre-ejection period (PEP) calculation results attained overall squared correlation coefficients of 0.9048 from SCG and 0.8350 from GCG with reference PEP from impedance cardiogram. Our results indicate that the proposed framework can improve the motion tolerance of cardio-mechanical signals in moving subjects. The effective number of recordings during day time could be potentially increased by the proposed framework, which will push forward the implementation of cardio-mechanical monitoring devices in mobile healthcare.

A Low-cost, Smartphone-only Pulse Transit Time Measurement System Using Cardio-mechanical Signals and Optical Sensors.

This paper presents a smartphone-only solution for measuring pulse transit time (PTT). An application based on an Android smartphone is developed to collect seismocardiogram (SCG), gyrocardiogram (GCG), and photoplethysmography (PPG) recordings. The system does not need any other external system for measurements, so the total cost and system complexity are minimized. PTT metrics are calculated as the time difference between the aortic valve opening points in the SCG or GCG signals recorded by the accelerometer or gyroscope of a smartphone respectively, and the fiducial points in the PPG signal recorded by a modified optical sensor connected to the audio input. A digital signal processing (DSP) system is developed in a post-processing environment and experimentally validated on ten healthy subjects at rest. Our results indicate that a smartphone-only PTT measurement system is feasible and comparable with stand-alone sensor node systems.